dsh-memory-vault：DSH 外置 SQLite 长期记忆（修复分支）
xs1023 维护的 dsh-memory-vault 是 hjj588 原版的外置记忆库修复分支，数据存于 ~/.dsh/memory/memory.db，兼容旧库无需迁移。修复对话记录重复、标题被宿主消息污染、长期压缩不可达与预设重复注入四类问题，并新增按工作区归属的项目维度与 scope 检索。安装：dsh plugin --profile web add github:xs1023/dsh-memory-vault，重启生效。支持分层记忆、归档搜索与 cordis.patch.yml 调参。
Read Moredsh-agent-memory：为 DSH Claw Agent 提供持久记忆
dsh-agent-memory 是 xingyingyuzhui 维护的 DSH 记忆类插件，为每个 Claw Agent 提供 USER/MEMORY 金库与按日日记，在 Claw 会话挂载 memory 工具，支持回合后回顾与 compaction/start 压缩前冲洗；可配置自由写或审批。安装命令为 dsh plugin --profile web add github:xingyingyuzhui/dsh-agent-memory，数据在 ~/.dsh/DSclaw/ 与 settings.json。工作区与官方会话不注入 Claw 记忆。MIT，0.1.10，Node >= 20。
Read Moredsh-memory-file：用 Markdown 文件做可核实的长期记忆
dsh-memory-file 为 DeepSeek Harness 提供基于 Markdown 的长期记忆：每会话首次 pre-step 注入记忆文件，并提供 memory_add、待审队列、撤销与 memory_status 等工具。默认不读 messages、不联网；可选 autoScan 只读本地会话日志中用户发言。维护者 wojiao42，MIT 许可，强调源码可审与 smoke.mjs 断言。
Read Moredsh-fount-memory：回合内召回的 Fount 风格持久记忆
dsh-fount-memory 由 win10ogod 维护，参考 Fount 长短期记忆设计，为 DeepSeek Harness 提供本机 SQLite 持久记忆。在模型请求前按关键词或日期触发命名事实召回，默认 recallCount 为 0、不自动注入完整对话轨迹，也不发起 followup/steer 或 dream 轮次。提供 remember、search、context、forget 四个工具，短期封存最近十条非空白消息供显式检索。安装使用官方 dsh plugin add 命令，适配 DSH 0.1.7-rc.2 至 0.2.1-alpha.1 与 format v4。
Read Moredsh-memory-jev：用 Jev 类型化判决为 DSH 记忆加三道门
dsh-memory-jev 是 Towzai 维护的 DSH 记忆插件：读写与可选上下文注入均经 TypeSafe Jev 做 choice/noul 判决，不生成记忆正文。提供 mem_remember、mem_recall 等工具，写入 fail-open、注入 fail-closed，含预算、审计与软删除。需 OPENROUTER_API_KEY，可配置 storePath 与注入阈值；安装命令为 dsh plugin --profile web install Towzai/dsh-memory-jev，进程级重启后用 mem_gate_status 确认。
Read Moredsh-memory-md：Markdown 长期记忆，中文可搜、无需 Web
dsh-memory-md 是 smallwhitelin 为 DeepSeek Harness 提供的极简长期记忆插件。以可手改的 Markdown 为真源，用大小写不敏感子串匹配解决 FTS5 对中文检索不友好问题，仅注入 tools 与 systemPrompt，适合纯 IM profile。提供 memory_add、replace、remove、search 四类工具与 maxInjectChars 等配置。安装可用 dsh plugin add github:smallwhitelin/dsh-memory-md 或 npm 包 dsh-memory-md。MIT 许可，Node ≥ 24。
Read Moredsh-memory-eternal-fork：DSH 本地 Markdown 记忆库维护版
dsh-memory-eternal-fork 是 EternalNight996/dsh-memory-eternal 的 MIT 维护 fork（pokiimon），npm 包 dsh-memory-eternal-fork v0.7.9，面向 DeepSeek Harness 提供本地 Markdown 记忆库：对话结束自动沉淀知识卡、memory_recall 按需召回、图形化审核与图谱。本文基于 README 介绍安装命令、配置要点、DSH 0.2.0-rc.x 兼容性修复及与上游 memory-eternal 新项目的关系，并提醒插件权限与社区目录性质。
Read More@tr1v3r/dsh-ltm：DSH 本地长期记忆与 CJK 感知检索
@tr1v3r/dsh-ltm 是 tr1v3r 为 DeepSeek Harness 维护的记忆类插件：本地 SQLite 存储，CJK 感知分词与 BM25+n-gram 混合检索，近重复检测、scope 隔离、过期复核与 prompt 召回预算；兼容 memory_write/search/forget 并扩展 update、confirm、list、merge 及 revision CAS。安装命令为 dsh plugin --profile <name> add @tr1v3r/dsh-ltm，默认库路径 $DSH_HOME/memory/ltm.db，不强制联网。本文基于 GitHub README 与 package.json 整理安装、配置与 CLI 用法，并说明从 dsh-memory 迁移与运行权限注意事项。
Read Moredsh-super-memory：跨压缩记忆插件
dsh-super-memory 是一个 DeepSeek Harness 跨压缩记忆插件。它解决超长会话压缩后模型遗忘旧结论的问题。核心功能包括压缩时自动入库、通过 BM25 检索相关内容并注入上下文，以及支持本地检索与可选大模型辅助。该插件仅限单会话使用，不依赖外部服务，支持 MIT 协议开源。
Read MoreDeepSeek Harness 插件：dsh-memory（跨会话记忆）
DeepSeek Harness 的 `dsh-memory` 插件通过插件化架构，填补了现有智能体开发中长对话记忆断层的空白。该插件核心功能包括：会话结束时自动总结对话内容、新会话开始时自动注入过往笔记，以及将数据本地存储在 `$DSH_HOME/memory/` 目录下。 它支持通过环境变量进行无UI配置，用户可灵活控制蒸馏频率、召回范围及文件大小等参数。该插件数据安全，不依赖会话日志，仅提供自动召回与自动蒸馏两条路径。
Read Moredsh-keepsake: DeepSeek Harness Cross-Session Memory Plugin
`dsh-keepsake` is a memory plugin for DeepSeek Harness, designed to resolve the loss of context caused by session resets. It automatically extracts and stores key information from conversations, such as personas and decisions, and automatically injects it into subsequent sessions. It also supports local memory management, editing, deletion, and backup. The plugin features semantic recall, has no external data dependencies, and stores data locally to ensure privacy and security. Once installed, it can be enabled in the DSH settings.
Read Moredsh-memory: DSH Advanced Auto-Memory Plugin
The dsh-memory plugin introduced by DeepSeek Harness (DSH) aims to address context window limitations in agent development. Built on local SQLite storage, it provides core features such as tiered memory, vector semantic retrieval, knowledge graph visualization, and worldline version management, supporting automatic memory injection, consolidation, and governance. In addition, the plugin offers advanced capabilities such as LLM distillation and global deduplication, and exposes the memory_* series of tool commands. Once installed, it can be enabled in a DSH environment and requires Node.js >= 22.19.
Read Moredsh-memvault: MemVault Memory Bridging Plugin for DeepSeek Harness
dsh-memvault is a memory plugin for DeepSeek Harness that connects MemVault storage with the DSH context. Through three core features—injection, extraction, and display—it dynamically loads local SQLite memories into the model's system prompt. The plugin provides a memory panel that supports viewing and editing core blocks, reviewing extraction results, and browsing stored content. After installation, ensure the MemVault pipeline is running; the plugin uses a Node.js module to connect directly to the database and automatically performs extraction when the session is idle, keeping memories persistent without blocking model responses.
Read MoreEcho Notes
Echo Notes is a locally encrypted emotional diary plugin built specifically for DeepSeek Harness. It supports emotion templates, timeline filtering, and the AES-256-GCM encryption algorithm, providing users with a private and structured journaling solution. The plugin integrates Agent-assisted writing, scheduled reminders, and automatic locking mechanisms, making it suitable for users who need local private journal management and want to use an agent to help organize their entries.
Read Moredsh-memory: A Cross-Session Long-Term Memory Plugin for DSH
`dsh-memory` is a local memory plugin for DeepSeek Harness (DSH) designed to address models' lack of cross-session memory. Built on local file-system storage and operating without LLM calls, it uses pure string matching and hash-based deduplication to enable zero-cost long-term memory persistence. Core features include multi-dimensional retrieval, conflict detection with a human adjudication mechanism, and audit logs. It injects memory into context through an L1, L2, and L3 three-tier structure, allowing the model to read and write memory on demand via tool calls. The plugin also provides a settings panel to manage memory, view usage, and resolve conflicts, making it well suited for workflows that require maintaining project context and preferences.
Read MoreDeepSeek Harness Memory Plugin: dsh-observational-memory
This plugin is designed to address the loss of contextual detail caused by compression in long DeepSeek Harness sessions. It continuously maintains an “observation–reflection–cleanup” pipeline in the background to consolidate session details before compression. Core features include compression rendering with zero model calls, evidence recovery via `recall`, and a session rollback button. Installation must meet specific version requirements, while configuration supports threshold control, model overrides, and debug options, making it suitable for long-conversation scenarios and helping ensure information continuity.
Read Moredsh-dream: A Plugin for Organizing and Reusing Task Experience
dsh-dream is a DeepSeek Harness plugin designed to address the issues of models forgetting context and repeatedly making the same mistakes. It helps users build long-term memory through automated extraction, structured storage, and a review mechanism. The plugin supports browsing and retrieval, automatic reuse of adopted experiences, manual review of dream diaries, and writing experience rules into documentation. After completing specific tasks, users can trigger automatic organization; once reviewed and adopted, related new tasks will automatically reuse these experiences, enabling the accumulation and reuse of agent capabilities.
Read MoreDeepSeek Harness Memory Plugin: A Hybrid Memory Solution Integrating Hermes Snapshots and Noema Retrieval
`dsh-hybrid-memory` is an open-source memory plugin for DeepSeek Harness, designed to combine the advantages of Hermes-style lightweight snapshots and Noema-style retrievable knowledge bases. The plugin uses a three-layer architecture (L1 snapshots, L2 knowledge base, and L3 tool imports), supporting local storage, Chinese full-text search (FTS5), and zero-context on-demand access. Data remains secure without external leakage, and the plugin requires a Node.js 22.5+ environment to run.
Read Moredsh-session-recycle-bin: DeepSeek Harness Session Recycle Bin
`dsh-session-recycle-bin` is a DeepSeek Harness plugin designed to address session accumulation. It provides a standard recycle bin mechanism, supporting quick sidebar deletion, bulk management via the settings panel, and true physical permanent deletion. With features such as active session protection, batch fault tolerance, and adaptive UI, it standardizes session lifecycle management and helps prevent accidental deletion of important data.
Read MoreDeepSeek Harness Plugin: dsh-followup-todo
The DeepSeek Harness plugin `dsh-followup-todo` provides users with cross-session todo management and supports building handoff context through Context and Inject fields. Installed via GitHub, it offers 4 model tools and a Web floating panel interface. Data is stored per workspace in JSON files, with support for priority, archiving, and filtering. Licensed under the MIT License, the project supports reviewing history, though data synchronization is not real-time and the Headless Profile does not include a UI.
Read MoreDeepSeek Harness (DSH) Memory Plugins: runfali/dsh-mem0-plugins
The DeepSeek Harness plugin `dsh-mem0-plugins` provides agents with persistent memory capability requiring no manual intervention. By integrating with a self-hosted `mem0-graph` server, it automatically retrieves relevant memories before generating answers and automatically converts conversation content into facts for write-back after the conversation ends. It also supports content masking and merged write-back for short conversations. The plugin provides tools such as `mem0_search` and requires configuration of the host, distillation model, and authentication parameters. It relies on Node.js >= 22 and a specific version of DSH, is released under the MIT license, and does not modify the source code.
Read Moredsh-ego-browser: Site Skill Memory for the DSH Browser Agent
`dsh-ego-browser` is a memory plugin for the DeepSeek Harness browser agent, designed to solve the problem of repeatedly learning site tool signatures and operation notes to improve efficiency. This MIT-licensed open-source plugin provides core features such as `ego_recall`, `ego_run`, and `ego_learn`, supporting tool registration, inherited storage, and environment checks. Installation requires Node.js 20 and `ego lite`, and has been validated in dsh v0.1.7-rc.2.
Read Moredsh-math-memory: A DeepSeek Harness Memory Assistant for Mathematical Notes
dsh-math-memory is a DeepSeek Harness assistant for mathematical note-taking, residing in Obsidian’s right sidebar. It addresses the limitation of general-purpose AI in maintaining context through a five-layer hierarchical memory system—profiles, topics, records, raw evidence, and inbox—and a unified retrieval protocol. The plugin provides cross-session context distillation, symbol-system maintenance, automated auditing, and feedback loops, enabling users to directly correct memory cards within AI responses. The current 0.7.x version is a prototype, while the upcoming 1.0 release will include full instructional and invocation features.
Read MoreMemory Standard Protocol (mm) for DeepSeek Harness
This plugin aims to provide a unified memory-sharing standard for the DeepSeek Harness (DSH) ecosystem. It builds a hierarchical memory structure based on pure Markdown files, defines the `mm` protocol, and supports cross-agent interoperability, deterministic budget management, and session snapshot mechanisms. The plugin provides CLI tools (such as `mem_read` and `mem_write`) and programming interfaces, ensuring that data is not silently truncated and serving as a cornerstone for building long-term memory systems.
Read Moredsh-papua-guinea: Papua New Guinea National Memory Plugin
The `dsh-papua-guinea` plugin for DeepSeek Harness (DSH) is designed to provide agents with country-specific knowledge about Papua New Guinea and falls under the “Memory” category. Implemented purely in Node.js, it can run offline and relies on DeepSeek-related toolkits. The installation command is `dsh plugin add github:uckkk/dsh-papua-guinea`. Since the source code does not expose detailed APIs, it is recommended to review the repository source to verify its behavior.
Read Moredsh-cerium (Cerium): A Network-Independent Memory Plugin
`dsh-cerium` is a pure Node.js memory plugin designed specifically for DeepSeek Harness (DSH). It aims to solve state persistence issues for agents in network-free or memory-constrained environments by completely removing dependencies on external storage and network requests. The plugin is maintained by uckkk, licensed under the MIT License, and is suitable for development scenarios that require offline execution or strict memory control. Users need to install specific dependencies and run the installation command; please refer to the source code for detailed usage.
Read MoreDeepSeek Harness Plugin: OpenClaw-Style Role File Loader
`askingtheheavens/dsh-openclaw-persona` is a plugin that encapsulates OpenClaw's rich file structure (such as SOUL.md, MEMORY.md, etc.) into a standard DSH Profile Bundle. It can automatically detect the `openclaw/` subdirectory in the workspace and map relevant files to a System Prompt or runtime context, thereby injecting OpenClaw's character identity and memory into DSH sessions without manual configuration. The plugin supports automatic loading of daily notes, file-watching refresh, and custom subdirectories, and takes effect after restarting DSH.
Read Moreevo: A Plugin for Providing Evolving Memory to Agents
evo is an alpha-stage open-source project that provides cross-session memory mechanisms for local CLI AI coding agents. Through a loop of “recall” and “reflection,” it uses SQLite to convert conversations into structured memory, supporting first-class skills, batch distillation, and multi-platform compatibility. The tool addresses the loss of agent state, enabling agents to maintain coherence by leveraging historical experience. It requires Node.js 22 or later.
Read MoreDSH CC-HAHA Memory: A Persistent Memory Plugin for DeepSeek Harness
dsh-cc-haha-memory is a memory plugin for DeepSeek Harness (DSH), designed to address the lack of persistent memory in native environments. It implements explicit, auditable memory storage through native events and tool calls, and supports standalone file management, project isolation, and a Web UI. It provides features such as automatic review, secure updates, and Claude memory import, injecting up to 5 memories per turn to prevent context pollution. The installation command is `dsh plugin --profile web add github:yihefeikong-rgb/dsh-cc-haha-memory`.
Read Moredsh-serum-concentration: Serum Concentration Reference
`dsh-serum-concentration` is a local “memory” plugin for DeepSeek Harness, maintained by uckkk. Using a pure Node tool named `serum_concentration`, it returns explicit recommendations based on input parameters, addressing the insufficient flexibility of hard-coded logic. It has no network dependencies and requires specific version dependencies. Developers can install it via a command and invoke it in a session. The plugin runs with the current process permissions and is suitable for scenarios requiring quick access to parameterized decision logic.
Read Moredsh-potassium: Potassium Element
The `dsh-potassium` memory plugin in the DSH ecosystem is maintained by developer uckkk and is licensed under the MIT open source license. It is a pure Node implementation with no network dependencies. Before installation, the version requirements for `@deepseek-ai/cordis` (^4.0.1) and `@deepseek-ai/dsh-tools` (>=0.1.0-rc.6) must be met. Developers can install it by running the `dsh plugin add github:uckkk/dsh-potassium` command. For more details, visit its GitHub repository or community directory.
Read Moredsh-barium: A Memory Plugin Implemented in Pure Node
`dsh-barium` is a pure Node.js memory processing plugin for DeepSeek Harness, requiring no network dependencies and maintained by developer uckkk. It depends on environments such as `@deepseek-ai/cordis`, and can be installed by running the command `dsh plugin add github:uckkk/dsh-barium`. It is integrated by configuring `cordis.patch.yml`, with the code logic located in `lib/index.js`. Since the plugin runs with the permissions of the current process, it is recommended to review the source code to confirm security before use. It provides a lightweight memory processing solution for the DSH ecosystem.
Read MoreDeepSeek Harness Persistent Memory Plugin: dsh-memory-panel
The `dsh-memory-panel` plugin provides persistent, searchable conversation memory management for DeepSeek Harness (DSH), addressing memory loss caused by process restarts. Its core features include memory tools (save, search, list, retrieve, and delete), highlighted memories automatically injected into system prompts, and a visual management panel with a JSON API. Data is stored in the `.dsh-memory` folder in the user's home directory, with concurrent write protection, weighted score-based sorting (title > tags > content), and Chinese word-segmentation search.
Read MoreDSH Documentation and Architecture Decision Records
The DSH plugin “Document and Architecture Decision Records,” developed by maintainer satan9394, is a memory-based plugin designed to provide documentation management and architecture decision record capabilities for DSH agents, enhancing long-term project maintainability. Its core features include storing and retrieving decision information. Users can obtain and install the plugin from the community directory or a GitHub repository, while being careful to review the source code and permissions. The plugin addresses DSH’s limitations in knowledge management and documentation.
Read Moredsh-daoing-memory: Self-Evolving Memory Plugin for DeepSeek Harness
`dsh-daoing-memory` is a persistent memory system designed for DeepSeek Harness (DSH) agents, intended to address signal flooding and hallucination contamination in conventional approaches. The plugin builds trust through an "earning" mechanism, classifies memories into semantic (facts and interests) and experiential (lifecycle experiences) types, and ensures data accuracy and traceability through an audit ledger and append-only logging. It provides end-to-end tooling for recording, extraction, recall, and auditing, with support for human intervention via a workbench. Developers must manually install the plugin and skills and restart the service; agents can then collaborate to build memories, converting only verified experiences into high-trust assets.
Read Moredsh-plugin-memory
`dsh-plugin-memory` is a plugin for DeepSeek Harness (DSH), designed to transform conversations into persistent knowledge through a Session Distillation mechanism. It automatically collects conversation content, distills it into structured JSON data, and persists it to a local directory, then registers it as a `memory-<slug>` skill for subsequent invocation. It supports automatic merging of similar entries and provides a `ctx.memory` service API for memory management. Installation options include installation via npm, installation via GitHub, or installation from a local tarball. Configuration options allow users to control automatic distillation, storage paths, and token limits. Note that the plugin currently lacks security policies and scope isolation, and all sessions share a single memory store.
Read Moredsh-tdai-memory: TencentDB Agent Memory Plugin for DeepSeek Harness
dsh-tdai-memory is an MIT-licensed plugin (v0.2.14, requiring Node >=22.18) for DeepSeek Harness (DSH), designed to provide a long-term memory layer for the Web profile. It enables memory retention and structuring through L0 conversation capture, L1 structured memory extraction (facts/preferences/events), L2 scenario generation, and L3 user profile construction. The core functionalities of the plugin include automatically recalling and injecting relevant memories as dynamic context during prompt assembly, as well as providing two search tools: `tdai_memory_search` and `tdai_conversation_search`. The installation method is via `dsh plugin`.
Read Moredsh-memory: Integrating LingShu Long-Term Memory into DeepSeek Harness
dsh-memory is a DSH memory plugin maintained by FuRongJun-1999 that integrates the LingShu (AEIS) Spatiotemporal Memory Engine into DeepSeek Harness. It provides cross-session recall/search, a knowledge flywheel, a white-box reasoning pipeline, self-awareness, and a v3.3 role-playing engine, along with a guardrail charter and full-chain audit. Installation requires first installing aeis via pip, then adding the plugin using `dsh plugin --profile` and configuring `dbPath` and `tools` mode in `cordis.yml`. It is suitable for AGI and interpretability research-oriented developers. Before use, please review the source code and the MIT license.
Read MoreEngramory: A Portable Markdown Memory Protocol for DeepSeek Harness Agents
Engramory (tinqiao-oss/engramory) is a zero-infrastructure memory protocol designed for AI agents: Markdown-based single-file-per-fact structure, four types of typed notes, explicit curation discipline, and bounded indexing. It has 171 stars on GitHub and is categorized as a memory tool in SkillHub. This article introduces its core capabilities, official SkillHub installation command, the engramory_init initialization process, index guard configuration, and considerations like single-writer/experimental status, helping DSH users set up auditable long-term working memory.
Read Moredsh-mnemon: Building a Three-Layer Pluggable Memory Control Plane for DeepSeek Harness
dsh-mnemon is a DSH memory plugin maintained by omdsh-dev. It manages context, project files, and long-term memory through a three-layer division of Runtime, Documents, and Memory Spaces. The third layer can integrate with nine providers, including Mnemon. This article introduces its core capabilities, installation commands under DSH 0.1.1-rc.2, a 5-minute verification process, as well as permissions, data boundaries, and applicable scenarios, enabling quick evaluation for integration after discovery on SkillHub.
Read Moredsh-memory-evolve: Equipping DeepSeek Harness with Long-Term Memory and Self-Evolution
dsh-memory-evolve is a DSH memory-type plugin maintained by csyangwen, which provides capabilities such as five-track cross-session memory, git branch awareness, four-track to-do lists, skill self-evolution, COI external AI scheduling, and session collaboration in a purely plugin-based manner, with zero core modifications and zero runtime dependencies. This article introduces its positioning, core features, installation commands, and typical usage, while also explaining community directory attributes and security considerations.
Read MoreUsing memtrace-public to add codebase structure memory to DeepSeek Harness
# memtrace-public This codebase is compiled into a structured knowledge graph that supports millisecond-level queries, covering functions, classes, call edges and versions, for DeepSeek Harness to use across sessions without repeatedly reading files. Maintained by syncable-dev, the community repository is categorized under the "Memory" category, and it had 454 stars as of August 18, 2026. The indexing is implemented via local Rust + Tree-sitter; the Harness plugin package `dsh-plugin-memtrace` is licensed under MIT, while the core indexer is under a proprietary EULA and is currently in private beta. This article cross-checks the installation commands, MCP tools, Skills, licenses and telemetry boundaries against the GitHub repository page.
Read MoreInstall verified MCP servers for DeepSeek Harness at once with dsh-mcp-bridge
**Translation:** dsh-mcp-bridge is a DeepSeek Harness community plugin maintained by Edge-Echo, which packages the official @deepseek-ai/dsh-mcp-client and a curated set of MCP servers into an installable bundle. By default, only the "everything" demo is enabled, with presets annotated for memory, filesystem, GitHub, Playwright and remote HTTP services. A verify script and CI connectivity checks are added via the servers/ directory definition. The project is categorized under the memory taxonomy. This article covers the directory page, cross-verified installation commands from GitHub and npm, capability boundaries and precautions.
Read MoreUsing dsh-kb-sieve to Build Auditable Local Knowledge Base for DeepSeek Harness
`dsh-kb-sieve` is a memory plugin for DeepSeek Harness maintained by omdsh-dev, which builds local knowledge packages with original text citations and SQLite FTS5 from md/txt/docx/pdf files. This paper verifies the capabilities of the three tools `kb_build`, `kb_query` and `kb_read` by cross-checking with the directory page and GitHub source code, covers the installation commands on the directory page, as well as usage boundaries including the PDF dependency `pdftotext`, incremental building and permission risks.
Read MoreEquip DeepSeek Harness with Readable and Editable Cross-Session Memory Using dsh-mneme
dsh-mneme is a DeepSeek Harness memory plugin maintained by modusensus, licensed under MIT. It uses native SQLite with editable Markdown for dual-writing cross-session memory, and offers autoDream background consolidation and optional offline semantic retrieval. This article verifies the installation commands, seven memory_* tools, configuration options, and notes based on the community directory page and GitHub README: the plugin runs with current dsh privileges, requires Node 24+, and has entity extraction and Sleep Mode disabled by default.
Read MoreConnect PowerContext Memory Service to DeepSeek Harness via powercontext-dsh
### 翻译结果（符合技术文档规范）： powercontext-dsh is an Apache-2.0 licensed DeepSeek Harness memory plugin maintained by knqiufan. It connects to a running PowerContext Server via HTTP, providing recall, memory, handover, experience and skill capabilities without embedding storage or using MCP. This article verifies the installation commands, pc_* tools, `/pc` command, configuration items and security boundaries against the community directory page and GitHub repository.
Read MoreConnecting DeepSeek Harness to a traceable academic research workbench with dsh-scholar
DSH-Scholar is a DeepSeek Harness community plugin maintained by lzszq, licensed under MIT. It is categorized under the memory category on the catalog page, which emphasizes retrieving, reading and summarizing literature within the agent loop; while the repository describes it as a research workspace for pure computational research, integrating materials, conversations, experiments, evidence ledgers and TeX manuscripts into the same recoverable project. It is gate-only by default, and agents cannot approve关卡 (levels/checkpoints) on their behalf. This article checks the installation commands, standalone workbench, Runner and typical slash commands against the catalog page and GitHub repository.
Read MoreDistill DSH Dialogue Experience into Reusable Skills with distill
distill is a memory plugin for DeepSeek Harness maintained by LoserFox: it only hooks into agent/turn-stopping and does not add tools to the main conversation. After each round ends, the background subagent will review every 3 new user messages by default, and write reusable processes into SKILL.md marked with `distilled-by: dsh-distill`. The directory installation command is `dsh plugin add github:LoserFox/distill`. It has been reported that the current version 0.1.0 has an issue where custom session events cause failure to load chat history on dsh 0.1.0-rc.6. Please check the source code, license and Issues before installation.
Read MoreInstall Local Hierarchical Memory for DeepSeek Harness with dsh-mnemon
DSH-Mnemon is a memory plugin for DeepSeek Harness maintained by omdsh-dev (MIT License, current version 0.2.2). It divides runtime memory, retrievable project archives and Mnemon memory into three layers. It uses local SQLite by default, and also supports connecting to nine types of providers such as Mem0. This article checks the installation command against the directory page and GitHub, as well as the first verification steps, cross-agent sharing boundaries and security considerations.
Read MoreAdd Cross-Session Long-Term Memory to DeepSeek Harness with dsh-memory-evolve
`dsh-memory-evolve` is a DeepSeek Harness memory plugin maintained by csyangwen (MIT License, JavaScript). It uses five-track memory, git branch filtering and confirmation-based writing to沉淀 project conventions, user preferences and progress into `~/.dsh/memories/`, eliminating the need to repeat everything from scratch when switching sessions. Capabilities such as skill evolution, four-track todo, COI scheduling and session broadcasting are also provided in the same repository, and most of them are disabled by default. The installation command on the directory page is `dsh plugin add github:csyangwen/dsh-memory-evolve`. The community plugin library has no official affiliation with DeepSeek / Horizon Robotics (Fang), and you should check the source code and license before installing.
Read MoreAdd persistent memory to DeepSeek Harness agent using mnemon
Mnemon is a persistent memory for LLM supervised agents maintained by mnemon-dev: it uses local SQLite four-graph storage, the host model determines what to remember, and the binary is responsible for indexing and recall. The community directory categorizes it under "Memory" and marks it as featured. This article verifies the installation commands, DSH configuration entry, CLI usage, and the relationship with dsh-mnemon according to the directory page and GitHub.
Read More